Recently, to ensure the reliability and safety of high-speed trains, detection and diagnosis of faults (FDD) in traction systems have become an active issue in the transportation area over the past two decades. Among these FDD methods, data-driven designs, that can be directly implemented without a logical or mathematical description of traction systems, have received special attention because of their overwhelming advantages. Based on the existing data-driven FDD methods for traction systems in high-speed trains, the first objective of this paper is to systematically review and categorize most of the mainstream methods. By analyzing the characteristic of observations from sensors equipped in traction systems, great challenges which may prevent successful FDD implementations on practical high-speed trains are then summarized in detail. Benefiting from theoretical developments of data-driven FDD strategies, instructive perspectives on this topic are further elaborately conceived by the integration of model-based FDD issues, system identification techniques, and new machine learning tools, which provide several promising solutions to FDD strategies for traction systems in high-speed trains.

High-speed trains have become one of the most important and advanced branches of intelligent transportation, of which the reliability and safety are still not mature enough for keeping up with other aspects. The first objective of this paper is to present a comprehensive review on the fault detection and diagnosis (FDD) techniques for high-speed trains. The second purpose of this work is, motivated by the pros and cons of the FDD methods for high-speed trains, to provide researchers and practitioners with informative guidance. Then, the application of FDD for high-speed trains is presented using data-driven methods which are receiving increasing attention in transportation fields over the past ten years. Finally, the challenges and promising issues are speculated for the future investigation.

Over the last decade, transfer learning has attracted a great deal of attention as a new learning paradigm, based on which fault diagnosis (FD) approaches have been intensively developed to improve the safety and reliability of modern automation systems. Because of inevitable factors such as the varying work environment, performance degradation of components, and heterogeneity among similar automation systems, the FD method having long-term applicabilities becomes attractive. Motivated by these facts, transfer learning has been an indispensable tool that endows the FD methods with self-learning and adaptive abilities. On the presentation of basic knowledge in this field, a comprehensive review of transfer learning-motivated FD methods, whose two subclasses are developed based on knowledge calibration and knowledge compromise, is carried out in this survey article. Finally, some open problems, potential research directions, and conclusions are highlighted. Different from the existing reviews of transfer learning, this survey focuses on how to utilize previous knowledge specifically for the FD tasks, based on which three principles and a new classification strategy of transfer learning-motivated FD techniques are also presented. We hope that this work will constitute a timely contribution to transfer learning-motivated techniques regarding the FD topic.

The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD approaches for nonlinear dynamic systems. More specifically, we parameterize nonlinear systems through a generalized kernel representation for system modeling and the associated fault diagnosis. An important result obtained is a unified form of kernel representations, applicable to both unsupervised and supervised learning. More importantly, through a rigorous theoretical analysis, we discover the existence of a bridge (i.e., a bijective mapping) between some supervised and unsupervised learning-based entities. Notably, the designed IFD approaches achieve the same performance with the use of this bridge. In order to have a better understanding of the results obtained, both unsupervised and supervised neural networks are chosen as the learning tools to identify the generalized kernel representations and design the IFD schemes; an invertible neural network is then employed to build the bridge between them. This article is a perspective article, whose contribution lies in proposing and formalizing the fundamental concepts for explainable intelligent learning methods, contributing to system modeling and data-driven IFD designs for nonlinear dynamic systems.

Incipient fault detection and diagnosis (FDD) is a key technology for enhancing safety and reliability of high-speed trains. This paper develops a real-time incipient FDD method named deep principal component analysis (DPCA) for electrical drive in high-speed trains. This method can effectively detect incipient faults in electrical drive before they develop into faults or failures. This scheme adopting multivariate statistics is composed of multiple data processing layers to extract more accurate signal features of electrical drive, which exhibits several salient advantages: 1) It can establish precise data models containing both systematic and noise information of electrical drive, which are helpful for incipient fault detection; 2) the incipient faults are described by multicharacteristics which can improve the fault diagnosis ability; 3) it can be easily implemented even if the system models and parameters of electrical drive are unknown. The effectiveness and feasibility of the proposed FDD scheme are authenticated via a mathematical analysis and validated via two experiments. Results of two experiments show that the missing alarm rate and detection delay by using the proposed DPCA-based FDD method are less than 10% and 0.68 s, respectively. In comparison with the standard PCA-based FDD method, the proposed DPCA-based FDD method can show its superiorities by the detailed performance comparisons.

Incipient faults in electrical drives can corrupt overall performance of high-speed trains; however, they are difficult to be discovered because of their slight fault symptoms. By sufficiently exploiting the distribution information of incipient faults, this paper presents the reason why incipient faults cannot be detected by the existing fault detection and diagnosis (FDD) methods. Under principal component analysis (PCA) framework, we propose a new data-driven FDD method, named probability-relevant PCA (PRPCA), for electrical drives in high-speed trains. The salient strengths of the PRPCA-based FDD method are: 1) It can greatly improve the fault detectability. 2) It is suitable for non-Gaussian electrical drives. 3) Based on the improved fault detectability, it can achieve accurate fault diagnosis via support vector machine (SVM). 4) It can be easily applied to electrical drives even if neither physical models or parameters nor expert knowledge of drive systems is given. 5) It is of highly computational efficiency that can meet requirements on the real-time FDD. A set of experiments on a dSPACE platform based traction system of the CRH2A-type high-speed train are carried out to demonstrate the effectiveness of the proposed method.